A A unifying framework Data Distribution Model for Fast Weights Slow Weights Updates Evaluation Supervised Learning S, Q C f

For readability, we omit OSAKA pre-training. Replay-based methods store representative samples from the past, either in their original form (e.g., rehearsal Most prior-based methods rely on task boundaries. Since non-stationary data distributions breaks the i.i.d assumption for The update is computed from a parametric combination of the gradient of the current and previous task. Despite that, meta-continual learning is actively researched [61, 6]. Bayesian change-point detection scheme to identify whether a task has changed.